1password 1.0.1

• Outcome: Review
• Latest audit: May 29, 2026 at 9:22 PM UTC
• Version:
  1.0.0

Overview

This appears to be a coherent 1Password CLI helper, but its examples normalize exposing secrets in files and terminal output without enough safeguards.

Install only if you are comfortable with the agent using your 1Password CLI context. Avoid examples that print secrets or use --no-masking, write secret output only to protected paths with restrictive permissions, exclude generated files from version control, and delete plaintext secret files after use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The example writes secret material directly to a local file (`./key.pem`) without any warning about filesystem exposure, permissions, cleanup, or accidental inclusion in backups and source control. In a secrets-management skill, normalizing unsafe secret-file handling can lead users to persist sensitive credentials in places that are easier to steal or mishandle.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: These examples print a secret-derived environment variable to stdout, and one disables masking with `--no-masking`, which directly encourages disclosure in terminals, shell history, logs, CI output, and screen recordings. In the context of a 1Password CLI skill, demonstrating secret exposure as a normal usage pattern materially increases the chance of credential leakage.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The example injects secrets into an output file (`config.yml`) without warning that the generated file now contains plaintext secrets. That can cause sensitive data to be left on disk, copied into artifacts, or committed to repositories, which is especially risky in documentation for a secrets tool.

VirusTotal

65/65 vendors flagged this skill as clean.